In [3]:
import seaborn as sns
import matplotlib.pyplot as plt
sns.countplot(x='Gender', hue='Exited', data=df)
plt.title('Abandono en función del Género')
plt.show()
pip install dash plotly
Requirement already satisfied: dash in c:\users\jlara\anaconda3\lib\site-packages (2.14.2) Requirement already satisfied: plotly in c:\users\jlara\anaconda3\lib\site-packages (5.9.0) Requirement already satisfied: Flask<3.1,>=1.0.4 in c:\users\jlara\anaconda3\lib\site-packages (from dash) (2.2.2) Requirement already satisfied: Werkzeug<3.1 in c:\users\jlara\anaconda3\lib\site-packages (from dash) (2.2.3) Requirement already satisfied: dash-html-components==2.0.0 in c:\users\jlara\anaconda3\lib\site-packages (from dash) (2.0.0) Requirement already satisfied: dash-core-components==2.0.0 in c:\users\jlara\anaconda3\lib\site-packages (from dash) (2.0.0) Requirement already satisfied: dash-table==5.0.0 in c:\users\jlara\anaconda3\lib\site-packages (from dash) (5.0.0) Requirement already satisfied: typing-extensions>=4.1.1 in c:\users\jlara\anaconda3\lib\site-packages (from dash) (4.7.1) Requirement already satisfied: requests in c:\users\jlara\anaconda3\lib\site-packages (from dash) (2.31.0) Requirement already satisfied: retrying in c:\users\jlara\anaconda3\lib\site-packages (from dash) (1.3.4) Requirement already satisfied: ansi2html in c:\users\jlara\anaconda3\lib\site-packages (from dash) (1.9.1) Requirement already satisfied: nest-asyncio in c:\users\jlara\anaconda3\lib\site-packages (from dash) (1.5.6) Requirement already satisfied: setuptools in c:\users\jlara\anaconda3\lib\site-packages (from dash) (68.0.0) Requirement already satisfied: importlib-metadata in c:\users\jlara\anaconda3\lib\site-packages (from dash) (6.0.0) Requirement already satisfied: tenacity>=6.2.0 in c:\users\jlara\anaconda3\lib\site-packages (from plotly) (8.2.2) Requirement already satisfied: Jinja2>=3.0 in c:\users\jlara\anaconda3\lib\site-packages (from Flask<3.1,>=1.0.4->dash) (3.1.2) Requirement already satisfied: itsdangerous>=2.0 in c:\users\jlara\anaconda3\lib\site-packages (from Flask<3.1,>=1.0.4->dash) (2.0.1) Requirement already satisfied: click>=8.0 in c:\users\jlara\anaconda3\lib\site-packages (from Flask<3.1,>=1.0.4->dash) (8.0.4) Requirement already satisfied: MarkupSafe>=2.1.1 in c:\users\jlara\anaconda3\lib\site-packages (from Werkzeug<3.1->dash) (2.1.1) Requirement already satisfied: zipp>=0.5 in c:\users\jlara\anaconda3\lib\site-packages (from importlib-metadata->dash) (3.11.0) Requirement already satisfied: charset-normalizer<4,>=2 in c:\users\jlara\anaconda3\lib\site-packages (from requests->dash) (2.0.4) Requirement already satisfied: idna<4,>=2.5 in c:\users\jlara\anaconda3\lib\site-packages (from requests->dash) (3.4) Requirement already satisfied: urllib3<3,>=1.21.1 in c:\users\jlara\anaconda3\lib\site-packages (from requests->dash) (1.26.16) Requirement already satisfied: certifi>=2017.4.17 in c:\users\jlara\anaconda3\lib\site-packages (from requests->dash) (2023.11.17) Requirement already satisfied: six>=1.7.0 in c:\users\jlara\anaconda3\lib\site-packages (from retrying->dash) (1.16.0) Requirement already satisfied: colorama in c:\users\jlara\anaconda3\lib\site-packages (from click>=8.0->Flask<3.1,>=1.0.4->dash) (0.4.6) Note: you may need to restart the kernel to use updated packages.
import pandas as pd
df = pd.read_csv("clientes.csv")
df = df.dropna()
print (df)
RowNumber CustomerId Surname CreditScore Geography Gender Age \
0 1 15634602 Hargrave 619 France Female 42.0
1 2 15647311 Hill 608 Spain Female 41.0
2 3 15619304 Onio 502 France Female 42.0
3 4 15701354 Boni 699 France Female 39.0
5 6 15574012 Chu 645 Spain Male 44.0
... ... ... ... ... ... ... ...
9997 9998 15584532 Liu 709 France Female 36.0
9998 9999 15682355 Sabbatini 772 Germany Male 42.0
9999 9999 15682355 Sabbatini 772 Germany Male 42.0
10000 10000 15628319 Walker 792 France Female 28.0
10001 10000 15628319 Walker 792 France Female 28.0
Tenure Balance NumOfProducts HasCrCard IsActiveMember \
0 2 0.00 1 1.0 1.0
1 1 83807.86 1 0.0 1.0
2 8 159660.80 3 1.0 0.0
3 1 0.00 2 0.0 0.0
5 8 113755.78 2 1.0 0.0
... ... ... ... ... ...
9997 7 0.00 1 0.0 1.0
9998 3 75075.31 2 1.0 0.0
9999 3 75075.31 2 1.0 0.0
10000 4 130142.79 1 1.0 0.0
10001 4 130142.79 1 1.0 0.0
EstimatedSalary Exited
0 101348.88 1
1 112542.58 0
2 113931.57 1
3 93826.63 0
5 149756.71 1
... ... ...
9997 42085.58 1
9998 92888.52 1
9999 92888.52 1
10000 38190.78 0
10001 38190.78 0
[9998 rows x 14 columns]
import seaborn as sns
import matplotlib.pyplot as plt
sns.countplot(x='Gender', hue='Exited', data=df)
plt.title('Abandono en función del Género')
plt.show()
import dash
from dash import dcc, html
from dash.dependencies import Input, Output
import plotly.express as px
import pandas as pd
df_grouped = df.groupby('Tenure')['Exited'].value_counts(normalize=True).unstack().fillna(0)
sorted_tenure_values = sorted(df['Tenure'].unique())
app = dash.Dash(__name__)
app.layout = html.Div([
html.H1("analisis de abandono de clientes en funcion de los años de permanencia "),
dcc.Dropdown(
id='tenure-dropdown',
options=[{'label': f'permanencia {tenure} años', 'value': tenure} for tenure in sorted_tenure_values],
value=min(sorted_tenure_values),
),
dcc.Graph(id='churn-pie-chart'),
])
@app.callback(
Output('churn-pie-chart', 'figure'),
[Input('tenure-dropdown', 'value')]
)
def update_pie_chart(selected_tenure):
selected_data = df[df['Tenure'] == selected_tenure]
fig = px.pie(selected_data, names='Exited', title=f'analisis cuando el cliente lleva en el banco {selected_tenure} años',
labels={'Exited': 'Churn Status'}, hole=0.4)
return fig
if __name__ == '__main__':
app.run_server(debug=True, port=8051)
import plotly.express as px
import pandas as pd
df_grouped = df.groupby('NumOfProducts')['Exited'].mean().reset_index()
fig = px.bar(df_grouped, x='NumOfProducts', y='Exited', color='NumOfProducts',
labels={'NumOfProducts': 'Número de Productos Financieros', 'Exited': 'Tasa de Abandono'},
title='Tasa de Abandono del Cliente en función del Número de Productos Financieros')
fig.show()
import plotly.subplots
import plotly.graph_objects as go
import pandas as pd
df_credit_card_no_churn = df[(df['HasCrCard'] == 1) & (df['Exited'] == 0)]
df_credit_card_churn = df[(df['HasCrCard'] == 1) & (df['Exited'] == 1)]
df_no_credit_card_no_churn = df[(df['HasCrCard'] == 0) & (df['Exited'] == 0)]
df_no_credit_card_churn = df[(df['HasCrCard'] == 0) & (df['Exited'] == 1)]
fig = plotly.subplots.make_subplots(rows=1, cols=1, subplot_titles=['Todos los Países'], shared_xaxes=True, shared_yaxes=True)
color_palette = px.colors.qualitative.Set1
fig.add_trace(go.Bar(x=['Con Tarjeta de Crédito', 'Sin Tarjeta de Crédito'],
y=[len(df[(df['HasCrCard'] == 1) & (df['Exited'] == 0)]),
len(df[(df['HasCrCard'] == 0) & (df['Exited'] == 0)])],
name='Todos los Países', marker_color=['lightblue', 'lightgreen']),
row=1, col=1)
buttons = [dict(label='Todos los Países',
method='update',
args=[{'visible': [True]}, {'title': 'Todos los Países'}])]
for i, country in enumerate(df['Geography'].unique()):
df_country = df[df['Geography'] == country]
color = color_palette[i % len(color_palette)]
fig.add_trace(go.Bar(x=['Con Tarjeta de Crédito', 'Sin Tarjeta de Crédito'],
y=[len(df_country[(df_country['HasCrCard'] == 1) & (df_country['Exited'] == 0)]),
len(df_country[(df_country['HasCrCard'] == 0) & (df_country['Exited'] == 0)])],
name=country, marker_color=color),
row=1, col=1)
buttons.append(dict(label=country,
method='update',
args=[{'visible': [False] * len(buttons) + [True]}, {'title': f'Clientes con/sin Tarjeta de Crédito y Abandono en {country}'}]))
fig.update_layout(updatemenus=[dict(type='dropdown', showactive=True, buttons=buttons, x=0.1, xanchor='left', y=1.1, yanchor='top')])
fig.show()
fig = px.scatter_3d(df, x='CreditScore', y='Balance', z='Age', color='Exited',
title='Gráfico de Dispersión 3D para CreditScore, Balance y Edad',
labels={'CreditScore': 'Puntuación de Crédito', 'Balance': 'Saldo', 'Age': 'Edad', 'Exited': 'Abandono'})
fig.show()
import seaborn as sns
import matplotlib.pyplot as plt
numeric_df = df[['CreditScore', 'Age', 'Tenure', 'Balance', 'NumOfProducts', 'HasCrCard', 'IsActiveMember', 'EstimatedSalary', 'Exited']]
correlation_matrix = numeric_df.corr()
plt.figure(figsize=(10, 8))
sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt='.2f')
plt.title('Mapa de Calor para Correlaciones entre Variables')
plt.show()
